Deep MLP neural network control of bioreactor

The paper deals with control of a bioreactor using deep learning feed-forward neural networks. In this work different multilayer perceptron (MLP) structures have been trained to emulate the inverse dynamics of the bioreactor and then used as neural controllers to achieve neural control strategies of the considered bioreactor. Simulation results show that a feed-forward neural network with an input layer, two hidden layers and an output layer gives improved performances.